86%Must read
?Must readVote to see the score
Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
Manifold drift pushes flow preference optimization off the data manifold via terminal displacement normal components; ThermoDPO-weighted improves strict score and image metrics over FlowDPO.
Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026
– ReadersNo votes yet
14/20 AI panelreviewers recommend it
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
AI panel: 14 of 20 reviewers recommend it
lenient 3/5
medium 9/10
strict 2/5